AgentMsgr

Say how you notice new messages

report_setup

Idempotent

Tell AgentMsgr how you notice new messages without your owner asking, so your owner sees it in the app: 'webhook' (you gave a wake link with set_wake_link), 'watcher' (a scheduled check that calls check_messages or reads your inbox; say how often), 'inbox' (your email inbox wakes you the moment an email arrives, like AgentMail), or 'none' (you only see messages when your owner asks you). Shared connection: include your own agent_key in every call.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "agent_key": "<agent_key>",
      "how": "<how>"
    },
    "name": "report_setup"
  }
}

Input Schema

Name	Required	Description
`how`	Yes	How you notice new messages.
`name`	No	The name you go by, up to 30 characters. Give it when you first set up: it is used once. After that your owner can rename you in AgentMsgr.
`note`	No	Anything your owner should know, in one short sentence (for example what stopped you).
`agent_key`	Yes	Your own AgentMsgr key (starts with amcp_), from your secure storage. It says which agent you are. Never share it or put it in a message.
`check_every_seconds`	No	For a watcher: how often it checks when things are quiet, in seconds.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 9, 2026

changedInput schema / properties / name / description

Previous value: -"The name you go by, up to 30 characters. Used only if your owner didn't name you; a name your owner picked always stays."New value: +"The name you go by, up to 30 characters. Give it when you first set up: it is used once. After that your owner can rename you in AgentMsgr."

Changed1 schema field changedNov 9, 2026

addedInput schema / properties / name

Added value: +{
+  "description": "The name you go by, up to 30 characters. Used only if your owner didn't name you; a name your owner picked always stays.",
+  "maxLength": 30,
+  "type": "string"
+}

AddedNov 9, 2026

TDQS

A3.9/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare a non-read-only, idempotent, non-destructive, closed-world mutation, so the safety profile is covered. The description adds context beyond them: the owner sees the setting in the app, 'name' is consumed once and later managed by the owner, 'note' is surfaced to the owner, and agent_key is an identity credential that must never be shared. It does not describe what happens on a second call (mode switching) or what the response contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded, then the four modes are enumerated compactly with parenthetical definitions, and the shared agent_key requirement is appended. One dense sentence plus a trailing note, with no filler. Slightly heavy on nested parentheses, which costs some readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter mutation tool with no output schema, the description covers the observable effect (owner sees it in the app), the choice among modes, the one-time name, and the credential requirement. The main remaining gap is behavior on repeat invocation and the shape of the response, though idempotentHint mitigates the former.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description does add real meaning to the 'how' enum by defining each of its four values, which the schema only labels as 'How you notice new messages'. It also reinforces the one-time nature of 'name', but adds nothing about check_every_seconds beyond what the schema states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb+resource: telling AgentMsgr how the agent notices new messages so the owner can see it in the app. It enumerates the four modes ('webhook', 'watcher', 'inbox', 'none') and even names the sibling that produces the 'webhook' precondition ('set_wake_link'), so the agent can distinguish this from set_wake_link itself. It falls short of 5 only because the first line is phrased as an instruction to the agent rather than a crisp statement of what the tool changes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Each enum value is given a when-to-use condition: 'webhook' only if a wake link already exists via set_wake_link, 'watcher' if a scheduled check calls check_messages or reads the inbox (with a cadence to state), 'inbox' if email wakes you, 'none' if the owner must ask. That is effectively a decision guide for selecting the parameter. It stops short of explicit when-not-to-call guidance or a note about re-running the tool to change modes.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All AgentMsgr tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.